agent-persistence
FeaturedEnable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
AI & Automation 211 stars
33 forks Updated today MIT
Install
Quality Score: 91/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Agent Persistence
Use this driver to activate or understand the `agent-persistence` addon:
```bash
aiwg use agent-persistence
```
The addon supplies deterministic gate definitions, not a replacement loop
runtime. Compose it with `agent-loop` or another orchestrator that supports
human checkpoints.
## Canonical gates
- `destructive-action-gate.yaml` requires authorization before destructive work.
- `false-positive-override-gate.yaml` records reviewed policy overrides.
- `recovery-escalation-gate.yaml` escalates bounded recovery failures.
Read the gate contract before integrating it, preserve its authorization
boundary, and use the owning loop's status surface to verify activation.
## References
- @$AIWG_ROOT/agentic/code/addons/agent-persistence/docs/hitl-integration.md
- @$AIWG_ROOT/agentic/code/addons/agent-loop/skills/agent-loop/SKILL.md
Details
- Author
- jmagly
- Repository
- jmagly/aiwg
- Created
- 1 years ago
- Last Updated
- today
- Language
- TypeScript
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
AI & Automation Listed
agents-agent-loop-guardrails
Bound agent autonomy with step budgets, spend caps, human gates, and checkpointing so failures stay cheap and debuggable.
1 Updated 5 days ago
aniruddhaadak80 AI & Automation Listed
human-in-the-loop-gate
Add a human approval checkpoint to an agent so it pauses before a risky or irreversible action (spending money, deleting data, sending messages, merging code) and resumes only after a human approves. Use when an agent acts autonomously on consequential operations.
1 Updated 2 weeks ago
imtiazrayhan AI & Automation Listed
agent-loops
Design agent goals, bounded loops, checkpoints, recovery, and stop conditions.
9 Updated today
fmind